按年被提到
20262026 · 3 次2026
AI 安全、伦理与社会影响›智能体安全与滥用·arXiv:2605.18991 · cs.CR

Agent Security is a Systems Problem

Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha, Johann Rehberger, Kamalika Chaudhuri, Xiaohan Fu, Khawaja Shams, Guy Amir, Jihye Choi, Sarthak Choudhary, Nils Palumbo 等 14 人 · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2026-05-20 · 最近 2026-07-17
3不同的人
2活跃月份
3讨论串
0被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness (the dominant viewpoint in the community) are insufficient on their own. Instead, we must complement existing efforts with techniques from the systems security domain. Based on our experience as cybersecurity researchers in operating systems, networks, formal methods, and adversarial machine learning, we articulate a set of core principles, grounded in decades of systems security research, that provide a foundation for designing agentic systems with predictable guarantees. As evidence, we analyze eleven representative real-world attacks on agents and discuss how systems principles, if realized, could have prevented these attacks. We also identify the research challenges that stand in the way of implementing these principles in agents.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论bradreaves2 · 2026-07

“This position paper argues that classic systems security design principles are what we need to secure AI agents.”

Agent Security Is a Systems Problem原评论 ↗
讨论串评论vrighter · 2026-07

“agent security is a very old lesson UNlearned. data and instructions don't mix. And agents can't separate them”

Agent Security Is a Systems Problem原评论 ↗
被提交为 story · 3 次